Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2844
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.06
     propOrder
    -0.95
    OGND
    -0.94
     kasarigan
    -0.92
     utafitiHapana
    -0.90
    AccessorTable
    -0.89
    CloseOperation
    -0.85
     Pries
    -0.83
    mybatisplus
    -0.83
    WebVitals
    -0.83
    POSITIVE LOGITS
    =$((
    0.47
     démarches
    0.41
    anser
    0.37
    ./
    0.37
     in
    0.36
     Protección
    0.36
    »
    0.35
     затем
    0.35
    şa
    0.35
     ideal
    0.35
    Activations Density 0.809%

    No Known Activations